knowledge-transfer-focus

knowledge-transfer-focus is a cursor rule for Cursor from SeanLF/weather-mcp. It costs 1,382 tokens per session, scanned A, original, MIT.

A writing rule for documenting solutions so that other team members understand the reasoning and can maintain the result.

In plain words
What is it for?
Use it when writing comments, explanations, design decisions, and maintenance guidance for technical work.
Why use it?
It prevents documentation from recording only the final answer by also explaining decisions, alternatives, and common changes.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/seanlf/weather-mcp/knowledge-transfer-focus
Clone the repo
git clone --depth 1 https://github.com/SeanLF/weather-mcp

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for knowledge-transfer-focus

README.md
[![agentmods](https://agentmods.dev/badge/rules/seanlf/weather-mcp/knowledge-transfer-focus.svg)](https://agentmods.dev/rules/seanlf/weather-mcp/knowledge-transfer-focus)
Your own site
<a href="https://agentmods.dev/rules/seanlf/weather-mcp/knowledge-transfer-focus"><img src="https://agentmods.dev/badge/rules/seanlf/weather-mcp/knowledge-transfer-focus.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,382 This file is loaded in full into every session.
When invoked 1,382 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01382 $0.01382
Opus 5 $0.00691 $0.00691
Sonnet 5 $0.00276 $0.00276
Haiku 4.5 $0.00138 $0.00138

Measured 3d ago against content hash 928bf14cb27d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-transfer-focus scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/knowledge-transfer-focus.mdc · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

filters:

  • type: event pattern: "documentation|knowledge_sharing"
  • type: content pattern: "(?i)(documentation|comment|explain|clarify)"

actions:

  • type: transform pattern: "^.*$" replacement: |

    Implementation with Knowledge Transfer

    Code with Contextual Documentation

    {original_content}

    Design Decisions

    Decision Alternatives Reasoning
    Retry mechanism with exponential backoff Single attempt with error Payment gateway occasionally has transient errors (5% of requests). Retries increase success rate by ~4%.
    Separate validation logging Combined with general error logging Helps security team identify potential fraud patterns separate from technical issues.
    Gateway selection based on amount Always use production gateway Test gateway has no fees but $1 limit, saving ~$150/month in processing fees for small test transactions.
    Event-driven notifications Polling for status Allows immediate updates to user and decoupling of payment processing from notification systems.

    Maintenance Guide

    Common Modification Scenarios

    1. Adding a new payment gateway provider

      • Files to modify: payment_gateways.py, gateway_factory.py, config.py
      • Considerations: Implement the PaymentGateway interface, add credential management, update gateway selection logic
    2. Modifying validation rules

      • Files to modify: payment_validator.py, validation_rules.py
      • Considerations: Update tests first, ensure backward compatibility with saved payment methods
    3. Changing retry behavior

      • Files to modify: process_payment.py, config.py
      • Considerations: Consider impact on user experience, gateway rate limits, and transaction timing

    Troubleshooting

    Symptom Likely Cause Resolution
    High rate of "Gateway timeout" errors Gateway API performance degradation Check gateway status, temporarily increase timeout, consider fallback gateway
    Increase in validation failures New card BIN range or rule change Update validation rules, check for potential fraud patterns
    Duplicate transactions Retry logic issue or client double-submission Check transaction IDs, implement idempotency keys
    Transaction recorded but customer not notified Event system failure Check event logs, manually trigger notifications, verify event subscriber health
  • type: suggest message: | For effective knowledge transfer:

    1. Document "why" not just "what" in your code
    2. Explain key design decisions and alternatives considered
    3. Create a maintenance guide for common modification scenarios
    4. Include troubleshooting information for likely issues
    5. Use clear, concise language that new team members can understand

examples:

  • input: | Here's my implementation of the payment processing module.

    def process_payment(payment_details, amount):
        # Validate payment details
        if not validate_payment_details(payment_details):
            return {'success': False, 'error': 'Invalid payment details'}
            
        # Process the payment with the payment gateway
        response = payment_gateway.charge(payment_details, amount)
        
        # Handle the response
        if response.status == 'success':
            save_transaction(response.transaction_id, payment_details, amount)
            return {'success': True, 'transaction_id': response.transaction_id}
        else:
            log_error(response.error_code, payment_details, amount)
            return {'success': False, 'error': response.error_message}
    

    output: |

    Implementation with Knowledge Transfer

Read the full file on GitHub · 157 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 157 lines · 1,382 tokens per session scan A 928bf14cb27d

Subscribe to this mod's changes

knowledge-transfer-focus is a cursor rule published in the GitHub repository SeanLF/weather-mcp (2 stars, last pushed 1y ago), licensed MIT. It adds 1,382 tokens to every session, about $0.0069 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.